Agent skill

Hook Mining

by Ootto-AI in Ootto-AI/claude-content-skills

Mine a CSV of REAL top-performing hooks and generate alternatives that keep what made them work: hold the storytelling psychology and structure fixed, hot-swap only the power words.

MITAuto-check passedDocuments & Office

Install Hook Mining

skills CLI
$ npx skills add Ootto-AI/claude-content-skills --skill hook-mining -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Ootto-AI/claude-content-skills hook-mining --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Ootto-AI/claude-content-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/hook-mining .claude/skills/hook-mining && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hook-mining
GitHub stars
112
Token cost
~1.2k tokens
SKILL.md length
516 words
Files
2
Skills in repo
51
Repo updated
First seen
Licence
MIT

At a glance

Mine a CSV of REAL top-performing hooks and generate alternatives that keep what made them work: hold the storytelling psychology and structure fixed, hot-swap only the power words.

  • Works in 3 steps: Get real hooks in → Mine it → Remix — the part that matters
  • The user has hook performance data (a Sandcastles / social-analytics export
  • SKILL.md covers 1. Get real hooks in, 2. Mine it, 3. Remix — the part that matters and Hard rules, plus 2 more sections
  • Runs Python scripts from its folder; calls python

What it does

Hook Mining is an agent skill from Ootto-AI/claude-content-skills. Mine a CSV of REAL top-performing hooks and generate alternatives that keep what made them work: hold the storytelling psychology and structure fixed, hot-swap only the power words. Use when the user has hook performance data (a Sandcastles / social-analytics export, scraped competitor hooks, their own analytics) and says "mine hooks", "remix hooks", "hook variations", "make hooks from this CSV", or "give me hook options from what's working". NOT for inventing hooks from nothing — that's viral-hook-writer.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `mine_hooks.py`).

It sits in Documents & Office, covering CSV and tabular files and Storytelling. The repository describes itself as: Free, copy-paste Claude skills that run your content growth factory — turn ideas + your NotebookLM memory into scroll-stopping Instagram reels. By Ootto. The licence is MIT.

When your agent uses it

  • The user has hook performance data (a Sandcastles / social-analytics export
  • Scraped competitor hooks
  • Their own analytics) and says mine hooks
  • Hook variations

Example prompts

  • “mine hooks”
  • “remix hooks”
  • “hook variations”
  • “/hook-mining”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Get real hooks in
  2. Mine it
  3. Remix — the part that matters

What it can do on your machine

Read from SKILL.md and the folder at commit 07b5294. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hook Mining loads about 1.2k tokens when it runs. Until then it costs about 131 tokens; SKILL.md has 516 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~131
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Ootto-AI/claude-content-skills at commit 07b5294, republished under its MIT licence (© Ootto-AI). 516 words, ~1,183 tokens.

Download SKILL.mdSave it as .claude/skills/hook-mining/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
hook-mining
description
Mine a CSV of REAL top-performing hooks and generate alternatives that keep what made them work: hold the storytelling psychology and structure fixed, hot-swap only the power words. Use when the user has hook performance data (a Sandcastles / social-analytics export, scraped competitor hooks, their own analytics) and says "mine hooks", "remix hooks", "hook variations", "make hooks from this CSV", or "give me hook options from what's working". NOT for inventing hooks from nothing — that's viral-hook-writer.
user-invokable
true
argument-hint
[path to your hooks CSV]
license
MIT
metadata.author
Ootto
metadata.version
1.0.0

Hook mining

Most AI hook writing is slop for one of two reasons: it copy-pastes a hook that worked for someone else, or it "rewrites" it until the English is flat and the psychology is gone.

This does neither. It keeps the data for what worked — the structure, the psychological mechanism, the rhythm — and swaps only the power words. Proven skeleton stays, skin changes.

1. Get real hooks in

You cannot mine what you do not have. The input is a CSV of hooks that actually performed:

  • a Sandcastles (sandcastles.ai) export — it analyses the top videos in your niche and ranks the best hooks; export that tab to CSV
  • any social-analytics export with a hook/title/caption column and a views/likes/score column
  • competitor hooks pulled with the agent-reach skill, or breakdowns from reel-analyzer

Column names are never predictable, so don't hand-parse.

2. Mine it

bash
python skills/hook-mining/mine_hooks.py hooks.csv [--top 40]

Auto-detects the hook column and the performance column, ranks, buckets by pattern, and flags the power words already present. Writes hooks.mined.json. Run --selftest to verify the parsing.

Patterns it sorts into: result-proof · time-bound · contrarian · secret-gap · listicle · how-to · warning-fear · newsjack · comparison · question · curiosity-tease · plain-statement.

3. Remix — the part that matters

For each hook worth reusing, produce 3–5 alternatives under one rule:

Keep the psychology. Swap the power words.

Hold fixed: the pattern, the clause order, the specificity (a number stays a number), the rhythm and syllable shape, the tension and where it resolves, the point of view.

Swap only: the charged words — the verb, the intensifier, the noun carrying the emotion. power_word_frequency in the mined JSON tells you which ones are earning their keep in your niche. Pull replacements from there, not from a thesaurus.

proven:   "You're using Claude wrong"                 [contrarian · you're + wrong]
  ✅      "You're prompting Claude backwards"          swapped the verb + the charge word
  ✅      "You're building agents the slow way"        same skeleton, same tension
  ❌      "Many people use Claude incorrectly"         psychology gone, flat English → slop
  ❌      "You're using Claude wrong"                  verbatim copy → plagiarism, the platform buries it

Then hand the winners to viral-hook-writer to rank, or straight into reel-scripter.

Show full SKILL.md (228 more words)Show less

Hard rules

  • Never ship a mined hook verbatim. It is someone else's line. Instagram's originality systems bury copies, and it's plagiarism. Model the technique, write your own words.
  • Never remix the structure. Change the clause order or drop the number and you have thrown away the only thing the data proved.
  • A number in the source stays a number in the remix — and it must be YOURS and real. Swapping in a stat you cannot defend is the fastest way to lose an audience.
  • Rank before you mine. Remixing a hook that did not perform just launders a bad idea.
  • Small buckets are signal. A pattern with two entries that both went viral beats one with forty mediocre ones. Weight by performance, not by count.

Failure modes

SymptomCauseFix
Variants read flat / corporaterewrote the sentence instead of swapping wordsrestore the original skeleton, change only the charged words
All variants sound identicalswapped one word in one slotvary the slot — verb, intensifier, or emotional noun
Variants lost the tensionresolved the curiosity gap inside the hookthe gap stays open; the payoff belongs after the hook
Nothing outperformsmining unranked or off-niche datare-export ranked, filter to the actual niche

Where it sits

agent-reach / reel-analyzer find what's working → hook-mining turns that data into your own hooks → viral-hook-writer ranks → reel-scripter writes the script → reel-builder builds it.

© Ootto-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/hook-mining of Ootto-AI/claude-content-skills.

  • SKILL.md
  • mine_hooks.py

Open the folder on GitHubat commit 07b5294

Compare with similar skills

Hook Mining next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hook Mining compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hook Mining this skillOotto-AI/claude-content-skills112—~1.2kAutomated safety check: PassMIT
PresentationRightNow-AI/openfang18k—~829Automated safety check: PassApache-2.0
Vdjdb Formatantigenomics/vdjdb-db157—~976Automated safety check: PassCustom licence
Graphic Case StudyVarnan-Tech/opendirectory674—~3.2kAutomated safety check: PassMIT
Champion Trackermajiayu000/claude-skill-registry6662 repos~1.1kAutomated safety check: NotesMIT
Data Table Managern8n-io/n8n207k—~2.3kAutomated safety check: PassCustom licence

Similar skills

  • Presentation

    RightNow-AI/openfang

    Presentation expert for slide structure, storytelling, visual design, and audience engagement

    18k GitHub stars~829 tokensUpdated 3 mo ago
    Documents & OfficeAuto-check passed
  • Vdjdb Format

    antigenomics/vdjdb-db

    Normalise the controlled-vocabulary fields of a raw VDJdb chunk TSV to the form the database records - IMGT V/D/J gene and allele names including Adaptive ImmunoSEQ and Arden conversions…

    157 GitHub stars~976 tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • Graphic Case Study

    Varnan-Tech/opendirectory

    Generates a professionally designed case study PDF for B2B SaaS sales and marketing.

    674 GitHub stars~3.2k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • Champion Tracker

    majiayu000/claude-skill-registry

    Track product champions for job changes and qualify their new companies against ICP.

    666 GitHub starsUsed in 2 repos~1.1k tokens
    Documents & OfficeAuto-check: notes
  • Official

    Load before calling data-tables or parse-file. An agent skill from n8n-io/n8n.

    207k GitHub stars~2.3k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Instrument Data To Allotrope

    aws-samples/amazon-bedrock-agents-healthcare-lifesciences

    Official

    Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV.

    274 GitHub starsUsed in 2 repos~2.7k tokens
    Documents & OfficeAuto-check passed

More from Ootto-AI/claude-content-skills

All 51 skills in this repo
  • Content Calendar

    Ootto-AI/claude-content-skills

    Turn a batch of ideas (or your content pillars) into a 2-week reel posting calendar with hooks, formats, and a daily plan.

    112 GitHub starsUsed in 1 repo~502 tokens
    Auto-check passed
  • Agent Reach

    Ootto-AI/claude-content-skills

    MUST USE when user wants to 调研/research/搜索/search/查/找/look up anything on the internet — e.g.

    112 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Ab Hook Tester

    Ootto-AI/claude-content-skills

    Generates two genuinely distinct hook variants for the same reel so you can post-test which opening actually wins.

    112 GitHub stars~484 tokensUpdated 1 mo ago
    Auto-check passed
  • AI Brain

    Ootto-AI/claude-content-skills

    Give Claude a permanent, searchable long-term memory using an Obsidian vault as the store.

    112 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Caption And Hashtags

    Ootto-AI/claude-content-skills

    Write the caption, hashtag set, and first comment for a reel or post.

    112 GitHub stars~508 tokensUpdated 1 mo ago
    Auto-check passed
  • Collab Outreach

    Ootto-AI/claude-content-skills

    Drafts personalized pitches to creators and brands for collab reels, shoutouts and partnerships.

    112 GitHub stars~489 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Hook Mining

What does Hook Mining do?

Mine a CSV of REAL top-performing hooks and generate alternatives that keep what made them work: hold the storytelling psychology and structure fixed, hot-swap only the power words. Hook Mining is an agent skill from Ootto-AI/claude-content-skills. Mine a CSV of REAL top-performing hooks and generate alternatives that keep what made them work: hold the storytelling psychology and structure fixed, hot-swap only the power words.

When should I use Hook Mining?

Hook Mining fits situations like: the user has hook performance data (a Sandcastles / social-analytics export; scraped competitor hooks; their own analytics) and says mine hooks; hook variations.

How do I install Hook Mining in Claude Code?

Run `npx skills add Ootto-AI/claude-content-skills --skill hook-mining -a claude-code`. Or copy the skill folder (skills/hook-mining in Ootto-AI/claude-content-skills) into .claude/skills/hook-mining in your project. Claude Code loads it when a task matches its description.

How do I install Hook Mining in Codex?

Run `npx skills add Ootto-AI/claude-content-skills --skill hook-mining -a codex`. Or copy the skill folder (skills/hook-mining in Ootto-AI/claude-content-skills) into .agents/skills/hook-mining in your project. Codex loads it when a task matches its description.

Can I use Hook Mining in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Ootto-AI/claude-content-skills --skill hook-mining -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hook-mining, .gemini/skills/hook-mining, .github/skills/hook-mining and .opencode/skills/hook-mining in your project.

What does Hook Mining need to run?

Going by SKILL.md and its folder, Hook Mining needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Hook Mining access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hook Mining safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hook Mining use?

Hook Mining is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hook Mining use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Hook Mining?

Skills that share tags, products or a category with Hook Mining: Presentation (RightNow-AI/openfang, 18k stars), Vdjdb Format (antigenomics/vdjdb-db, 157 stars), Graphic Case Study (Varnan-Tech/opendirectory, 674 stars) and Champion Tracker (majiayu000/claude-skill-registry, 666 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hook Mining?

Ootto-AI (a GitHub organization) maintains it in Ootto-AI/claude-content-skills, which has 112 GitHub stars. The repository holds 51 skills in this directory. The repository was last updated on August 23, 2026.

Source: Ootto-AI/claude-content-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.